Artificial intelligence and machine learning applications are increasingly prevalent in the healthcare industry. In some cases, medical devices use sensor-collected data to feed into algorithms which generate scores or risk assessments that are used to inform patient care. The process of determining sensor accuracy requirements which will ensure that the algorithm generates reliable scores is not straightforward or well-defined. In this paper, we describe a simulation-based method to characterize sensor accuracy requirements for a device that uses a machine-learning algorithm to generate a postural stability score – the ZIBRIO Stability Scale. The results of the simulation are described, as is the application to sensor selection in preparation for manufacturing of the device. Other medical device developers may be able to use this method or similar methods in their requirements engineering process.

Background: 29% of older adults fall annually, resulting in the leading cause of accidental death. Fall prevention programs typically include exercise training and self-monitoring of physical activity has a positive effect on the self-efficacy and self-regulation of exercise behaviors. We assessed if self-monitoring of fall risk, without an intervention, impacts fall rates.Methods: Fifty-three older adults had open access to a balance measuring platform which allowed them to self-monitor their postural stability and fall risk using a simple 1-min standing balance test. 12-month retrospective fall history was collected and a monthly/bimonthly fall log captured prospective falls. Participants had access to self-monitoring for up to 2.2 years. Fall history and fall incidence rate ratios and their confidence intervals were compared between the periods of time with and without access to self-monitoring.Results: A 54% reduction in the number of people who fell and a 74% reduction in the number of falls was observed when participants were able to self-monitor their postural stability and fall risk, after normalizing for participation length. Further, 42.9% of individuals identified as having high fall risk at baseline shifted to a lower risk category at a median 34 days and voluntarily measured themselves for a longer period of time.Discussion: We attribute this reduction in falls to changes in health behaviors achieved through empowerment from improved self-efficacy and self-regulation. Providing older adults with the ability to self-monitor their postural stability and intuit their risk of falling appears to have modified their health behaviors to successfully reduce fall rates.

Introduction: Falls are the leading cause of accidental death in older adults. Each year, 28.7% of US adults over 65 years experience a fall resulting in over 300,000 hip fractures and $50 billion in medical costs. Annual fall risk assessments have become part of the standard care plan for older adults. However, the effectiveness of these assessments in identifying at-risk individuals remains limited. This study characterizes the performance of a commercially available, automated method, for assessing fall risk using machine learning.Methods: Participants (N = 209) were recruited from eight senior living facilities and from adults living in the community (five local community centers in Houston, TX) to participate in a 12-month retrospective and a 12-month prospective cohort study. Upon enrollment, each participant stood for 60 s, with eyes open, on a commercial balance measurement platform which uses force-plate technology to capture center-of-pressure (60 Hz frequency). Linear and non-linear components of the center-of-pressure were analyzed using a machine-learning algorithm resulting in a postural stability (PS) score (range 1–10). A higher PS score indicated greater stability. Participants were contacted monthly for a year to track fall events and determine fall circumstances. Reliability among repeated trials, past and future fall prediction, as well as survival analyses, were assessed.Results: Measurement reliability was found to be high (ICC(2,1) [95% CI]=0.78 [0.76–0.81]). Individuals in the high-risk range (1-3) were three times more likely to fall within a year than those in low-risk (7–10). They were also an order of magnitude more likely (12/104 vs. 1/105) to suffer a spontaneous fall i.e., a fall where no cause was self-reported. Survival analyses suggests a fall event within 9 months (median) for high risk individuals.Conclusions: We demonstrate that an easy-to-use, automated method for assessing fall risk can reliably predict falls a year in advance. Objective identification of at-risk patients will aid clinicians in providing individualized fall prevention care.

The Zibrio SmartScale is a low-cost, portable force platform designed to perform an objective assessment of postural stability. The purpose of the present study was to validate the center of pressure (COP) measurements in the Zibrio SmartScale. Simultaneous COP data was collected by a Zibrio SmartScale and a laboratory-grade force platform (LFP) under the dynamic motion of an inverted pendulum device intended to mimic the sway of a standing human. The inverted pendulum was placed on the Zibrio SmartScale which was placed on the LFP. The pendulum was then displaced to angles of 3 degrees and 5 degrees in both the anterior-posterior (AP) and medial-lateral (ML) directions. The findings of this study show low mean average error (MAE) among the measures taken simultaneously upon the LFP and Zibrio SmartScale with no appreciable difference in error in either AP or MLCOP directions. Averaged over repeated trials, the MAE did not surpass 0.5 mm. This represented 0.4% of the total range (+/- 50 to 60 mmin 5 degrees displacement trials) of simulated COP. The results of this study strongly indicate that the Zibrio SmartScale can perform adequately as a lightweight and low-cost alternative method of COP measurement in comparison to a traditional LFP. (C) 2019 Elsevier Ltd. All rights reserved.

A software package reads and analyzes pressure distributions from sensors mounted under a person's feet. Pressure data from sensors mounted in shoes, or in a platform, can be used to provide a description of postural stability (assessing competence to deficiency) and enables the determination of the person's present activity (running, walking, squatting, falling). This package has three parts: a preprocessing algorithm for reading input from pressure sensors; a Hidden Markov Model (HMM), which is used to determine the person's present activity and level of sensing-motor competence; and a suite of graphical algorithms, which allows visual representation of the person's activity and vestibular function over time.

Balance deterioration is a major risk factor for falling, particularly among the elderly. Early detection of emerging balance problems can allow behavioral and medical interventions to reduce the impact and severity of balance-related incidents. The iBalance technology presents a small, mobile platform that integrates hardware and software engineering for balance monitoring at a low cost for use in the home, physical therapy office, or other point of care setting. The hardware solution has the form factor of a bathroom scale and takes the standard approach of a force plate with four load cells arranged in the corners beneath the platform. The load cells output 12-bit data to a computing device running the accompanying software. There is less scientific consensus about the most effective software solution for performing analysis on balance data. A survey of the literature reveals 16 commonly used metrics of balance derived from force plate data. Using principal component analysis, we identify three underlying clusters of metrics from which a representative metric for each cluster may be chosen to construct an exogenous balance score. Finally, we have developed a graphical user interface for the iBalance that allows researchers to collect raw and/or processed data and view analytic visualizations of the data, with ease of extensibility for further research and analysis.

We propose a technique to estimate functional limits of stability (LOS) during bipedal stance using a controlled, low speed, voluntary leaning protocol requiring feet to remain in contact with the ground. LOS are estimated from ellipses fit to center-of-mass position data obtained during the leaning protocol. The LOS of nine healthy subjects were found to be 20–59% closer to the center of stance than the more frequently used anatomical boundaries and were reduced by closing the eyes. We conclude that functional stability boundaries should be used when the outcome measure is related to fall risk.

examined visual-vestibular fusion during roll tilt using three conditions

Introduction: Recent work indicates mechanical stimulation of soles may attenuate muscle atrophy initiated by gravitational unloading, including that experienced during spaceflight. The aim of the present study was to determine the modulating effect of unloading and body configurations on the neuromuscular response to mechanical foot stimulation. Methods: A solenoid (2.5-cm(2) surface area) embedded within a platform provided non-noxious stimulation to the lateral foot sole: 100 ms duration, 3-mm protrusion. Stimulation was applied while measuring root mean square electromyography of the soleus and lateral gastrocnemius. Experiment 1 compared seated and standing conditions, as well as different levels of gravitational unloading created by suspension. Experiment 2 altered postural stability by varying leg stance widths during a static stepping posture. Either the foot of the support leg or the nonsupport leg was stimulated. Reduced levels of loading further altered the level of postural challenge and support while maintaining the same body configuration. Results: In both experiments, loading was not a modulating factor to the response, supporting the use of mechanical foot pressure as a countermeasure for spaceflight. Body configuration and postural instability both modulated the response, independently of load. Discussion: In conclusion, an application of dynamic foot stimulation could be used to elicit neuromuscular activity without the need of background muscle activity or gravitational loading. However, the body configuration of the user with respect to postural stability needs to be considered in the application, and may provide further scope of benefits extending to the activation of postural synergies.

Since the early days of human spaceflight it has been reported that extended exposure to gravitational unloading results in a myriad of neuromotor adaptations that, while appropriate for microgravity, are maladaptive upon return to Earth. If not countered, these adverse effects of microgravity can result in negative health consequences and place crewmembers at risk for injury. The most commonly used countermeasures in today's space programs are those requiring active participation in prescribed exercise regimes that are time intensive, not completely effective, and have led to relatively low compliance. In this paper we review evidence that suggests a "passive" countermeasure in the form of dynamic foot stimulation (DFS) to the plantar surfaces of the feet may be a useful supplement to more traditional exercise countermeasures. This includes reports from both Russian and American investigators using both human and animal models indicating the overall effectiveness of DFS, the specific stimulation parameters involved, and a physiological explanation for the outcomes associated with the exposure to microgravity. Additionally, the use of DFS has the potential to benefit those at risk for muscle atrophy, including those experiencing extended bedrest, the elderly, and those with spinal cord injuries.

Increased postural instability and the subsequent elevation in fall incidence with increasing age are important contributors for hip fractures and developing frailty. When testing for such instability, most studies characterize balance in terms of center-of-mass (COM) deviation from a finite point, the "equilibrium point", located at the center of a subject's stance. For example, the clinically accepted equilibrium score (EQscore) represents instability as the maximum peak-to-peak sway about the "equilibrium point". An alternative theory views balance as being controlled within a "stability margin" in which all corrective actions are based on the time to contact (TTC) of the body's COM with that margin. This study examines the differences offered by evaluating balance control using the EQscore and TTC approach across several age groups and sessions. Consenting subjects from the Baltimore Longitudinal Study of Aging were recruited (N=155) from each age decade (20s-80s) who were generally healthy and free from neurological diagnoses. Results showed TTC tests detected significant variations in eyes open versus eyes closed testing that were unpredictable by EQscore. Further, TTC produced differences in age-related stability threats not seen using EQscore. The TTC data also provided a discriminating difference between subjects who fell in the difficult tests and those who maintained posture. Overall, these data suggest EQscore might not sufficiently account for dynamic control components the body may be using to maintain balance. TTC may offer a more accurate estimate of postural stability (functional ability) than EQscore based on its inclusion of a velocity component to detect dynamic changes.

Objective: The aim of the present study was to determine the modulating effect of background muscle activity on enhanced neuromuscular responses to mechanical foot stimulation.Design: A small solenoid embedded within a platform provided non-noxious stimulation to the lateral portion of the sole for 100 msecs at a 3-mm protrusion. The stimulation was applied during different contraction levels of the homonymous muscle and of remote, Jendrassik-like contractions. Peak amplitudes of the neuromuscular responses were measured from the soleus and lateral gastrocnemius muscles using root mean square electromyography.Results: Homonymous muscle contraction linearly increased peak amplitudes of the neuromuscular response induced by foot stimulation. Remote muscle contractions did not modulate the response. In all conditions, peak amplitudes of the reflex response reached 80-100% of maximal contraction levels. There was also a prolonged inhibition of homonymous contractions that lasted approximately 55 msecs after the excitatory neuromuscular response.Conclusions: An application of mechanical foot stimulation enhanced neuromuscular activity of the triceps surae muscles; this enhancement was dependent on homonyomous background contraction levels.

The purpose of the present experiment was to compare in normal human subjects the differential effects on postural stability of introducing somatosensory noise via compliant and/or sway-referenced support surfaces during quiet standing. The use of foam surfaces (two thicknesses: thin (0.95cm) and thick (7.62cm)) and sway-referenced support allowed comparison between two different types of destabilizing factors that increased ankle/foot somatosensory noise. Under some conditions neck extensions were used to increase sensory noise by deviating the vestibular system from its optimal orientation for balance control. The impact of these conditions on postural control was assessed through objective measures of instability. Thick foam and sway-referenced support conditions generated comparable instability in subjects, as measured by equilibrium score and minimum time-to-contact. However, simultaneous application of the conditions resulted in greater instability, suggesting a higher level of generated sensory noise and thus, different receptor types affected during each manipulation. Indeed, sway-referenced support generated greater anterior-posterior center-of-mass (COM) sway, while thick foam generated greater medio-lateral COM sway and velocity. Neck extension had minimal effect on postural stability until combined with simultaneous thick foam and sway-referenced support. Thin foam never generated enough sensory noise to affect postural stability even with noise added by sway-reference support or neck extension. These results provide an interesting window into the central integration of redundant sensory information and indicate the postural impact of sensory inputs is not solely based on their existence, but also their level of noise.

Removal of the mechanical pressure gradient on the soles leads to physiological adaptations that ultimately result in neuromotor degradation during spaceflight. We propose that mechanical stimulation of the soles serves to partially restore the afference associated with bipedal loading and assists in attenuating the negative neuromotor consequences of spaceflight. A dynamic foot stimulus device was used to stimulate the soles in a variety of conditions with different stimulation locations, stimulation patterns and muscle spindle input. Surface electromyography revealed the lateral side of the sole elicited the greatest neuromuscular response in ankle musculature, followed by the medial side, then the heel. These responses were modified by preceding stimulation. Neuromuscular responses were also influenced by the level of muscle spindle input. These results provide important information that can be used to guide the development of a "passive" countermeasure that relies on sole stimulation and can supplement existing exercise protocols during spaceflight.